Upload tokenizer

added_tokens.json

@@ -1,4 +1,5 @@
 {
+  "<|endoftext|>": 32002,
   "<|im_end|>": 32001,
   "<|im_start|>": 32000
 }

special_tokens_map.json

@@ -1,14 +1,14 @@
 {
   "additional_special_tokens": [
     {
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<|im_end|>",
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -29,7 +29,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -47,6 +47,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32002,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -42,11 +42,19 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32002": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+    "<|im_end|>",
+    "<|endoftext|>"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,